mm/pgtable: add pte_free_defer() for pgtable as page

Add the generic pte_free_defer(), to call pte_free() via call_rcu().
pte_free_defer() will be called inside khugepaged's retract_page_tables()
loop, where allocating extra memory cannot be relied upon.  This version
suits all those architectures which use an unfragmented page for one page
table (none of whose pte_free()s use the mm arg which was passed to it).

Link: https://lkml.kernel.org/r/78e921b0-b681-a1b0-dc20-44c9efa4ef3c@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zack Rusin <zackr@vmware.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 51d04c1847c11362a67d967ce893de17439d10e5..1fc4b9c2c8a68c4c0ec0eb5240ccbe43520aefa3 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -144,6 +144,10 @@ struct page {
                struct {        /* Page table pages */
                        unsigned long _pt_pad_1;        /* compound_head */
                        pgtable_t pmd_huge_pte; /* protected by page->ptl */
+                       /*
+                        * A PTE page table page might be freed by use of
+                        * rcu_head: which overlays those two fields above.
+                        */
                        unsigned long _pt_pad_2;        /* mapping */
                        union {
                                struct mm_struct *pt_mm; /* x86 pgds only */

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 7f2db400f65342a31b18cab7bec9f54ab91c53e6..9fa34be65159c78c446e6fe69eb67bea5abea272 100644 (file)
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -112,6 +112,8 @@ static inline void pte_unmap(pte_t *pte)
 }
 #endif
 
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
 /* Find an entry in the second-level page table.. */
 #ifndef pmd_offset
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)

diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index b9a0c2137cc13530eaaea5812ea1172ae447cd59..fa9d4d08429124936df7bed95bfe2ae554946caa 100644 (file)
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -13,6 +13,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/mm_inline.h>
+#include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
 /*
@@ -230,6 +231,25 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
        return pmd;
 }
 #endif
+
+/* arch define pte_free_defer in asm/pgalloc.h for its own implementation */
+#ifndef pte_free_defer
+static void pte_free_now(struct rcu_head *head)
+{
+       struct page *page;
+
+       page = container_of(head, struct page, rcu_head);
+       pte_free(NULL /* mm not passed and not used */, (pgtable_t)page);
+}
+
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+       struct page *page;
+
+       page = pgtable;
+       call_rcu(&page->rcu_head, pte_free_now);
+}
+#endif /* pte_free_defer */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \